AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values

@inproceedings{Sarma2018AISA,
  title={AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values},
  author={G. Sarma and N. J. Hay and A. Safron},
  booktitle={SAFECOMP Workshops},
  year={2018}
}
  • G. Sarma, N. J. Hay, A. Safron
  • Published in SAFECOMP Workshops 2018
  • Computer Science
  • We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of artificial intelligence has been sufficiently validated to play a role in the design of AI systems. 

    Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES
    The subthalamic nucleus, oscillations, and conflict.
    65
    Network Resilience in Future Optical Networks
    17
    Towards a strategy for software requirements selection
    97
    Searching for Elements in Black Box Fields and Applications
    23
    Supporting 3D window manipulation with a yawing mouse
    17
    Doing things twice (or differently): Strategies to identify studies for targeted validation
    3
    When Will AI Exceed Human Performance? Evidence from AI Experts
    188